Index

A

abs_path_or_model_dir_path() (in module pimlico.core.paths) add_data_points() (pimlico.datatypes.features.IndexedTermFeatureListCorpusWriter method) (pimlico.datatypes.IndexedTermFeatureListCorpusWriter method) add_document() (pimlico.datatypes.tar.TarredCorpusWriter method) (pimlico.datatypes.TarredCorpusWriter method) add_documents() (pimlico.datatypes.dictionary.DictionaryWriter method) (pimlico.datatypes.DictionaryWriter method) add_execution_history_record() (pimlico.core.modules.base.BaseModuleInfo method) AddAnnotationField (class in pimlico.datatypes) (class in pimlico.datatypes.word_annotations) AlignedTarredCorpora (class in pimlico.datatypes) (class in pimlico.datatypes.tar)

all_dependencies() (pimlico.core.dependencies.base.SoftwareDependency method) annotation_fields (pimlico.datatypes.word_annotations.WordAnnotationCorpus attribute) (pimlico.datatypes.WordAnnotationCorpus attribute) AnnotationParseError, [1] archive_iter() (pimlico.core.modules.map.filter.DocumentMapOutputTypeWrapper method) (pimlico.datatypes.AlignedTarredCorpora method) (pimlico.datatypes.TarredCorpus method) (pimlico.datatypes.tar.AlignedTarredCorpora method) (pimlico.datatypes.tar.TarredCorpus method) array (pimlico.datatypes.arrays.NumpyArray attribute) (pimlico.datatypes.NumpyArray attribute) (pimlico.datatypes.ScipySparseMatrix attribute) (pimlico.datatypes.arrays.ScipySparseMatrix attribute) available() (pimlico.core.dependencies.base.SoftwareDependency method)

B

BaseModuleExecutor (class in pimlico.core.modules.base)

BaseModuleInfo (class in pimlico.core.modules.base)

C

CaevoCorpus (class in pimlico.datatypes) (class in pimlico.datatypes.caevo) call_java() (in module pimlico.core.external.java) CandcOutputCorpus (class in pimlico.datatypes) (class in pimlico.datatypes.parse) (class in pimlico.datatypes.parse.candc) CandcOutputCorpusWriter (class in pimlico.datatypes) (class in pimlico.datatypes.parse) (class in pimlico.datatypes.parse.candc) check_and_install() (in module pimlico.core.dependencies.base) check_cmd() (in module pimlico.cli.check) check_for_cycles() (in module pimlico.core.config) check_for_error() (pimlico.core.modules.map.InputQueueFeeder method) check_java() (in module pimlico.core.dependencies.java) check_java_dependency() (in module pimlico.core.dependencies.java) check_pipeline() (in module pimlico.core.config) check_ready_to_run() (pimlico.core.modules.base.BaseModuleInfo method) (pimlico.core.modules.multistage.MultistageModuleInfo method) check_release() (in module pimlico.core.config) check_runtime_dependencies() (pimlico.core.modules.base.BaseModuleInfo method) (pimlico.datatypes.NumpyArray method) (pimlico.datatypes.PimlicoDatatype method) (pimlico.datatypes.ScipySparseMatrix method) (pimlico.datatypes.arrays.NumpyArray method) (pimlico.datatypes.arrays.ScipySparseMatrix method) (pimlico.datatypes.base.PimlicoDatatype method) check_type() (in module pimlico.core.modules.base) (pimlico.datatypes.DynamicInputDatatypeRequirement method) (pimlico.datatypes.WordAnnotationCorpusWithRequiredFields method) (pimlico.datatypes.base.DynamicInputDatatypeRequirement method) (pimlico.datatypes.word_annotations.WordAnnotationCorpusWithRequiredFields method) choose_from_list() (in module pimlico.core.modules.options) clear_output_queues() (pimlico.core.external.java.Py4JInterface method) cmdloop() (pimlico.cli.shell.base.DataShell method)

comma_separated_list() (in module pimlico.core.modules.options) comma_separated_strings() (in module pimlico.core.modules.options) commands (pimlico.cli.shell.base.ShellCommand attribute) CoNLLDependencyParseCorpus (class in pimlico.datatypes) (class in pimlico.datatypes.parse) (class in pimlico.datatypes.parse.dependency) CoNLLDependencyParseCorpusWriter (class in pimlico.datatypes) (class in pimlico.datatypes.parse) (class in pimlico.datatypes.parse.dependency) CoNLLDependencyParseInputCorpus (class in pimlico.datatypes) (class in pimlico.datatypes.parse) (class in pimlico.datatypes.parse.dependency) CoNLLDependencyParseInputCorpusWriter (class in pimlico.datatypes) (class in pimlico.datatypes.parse) (class in pimlico.datatypes.parse.dependency) ConstituencyParseTreeCorpus (class in pimlico.datatypes) (class in pimlico.datatypes.parse) ConstituencyParseTreeCorpusWriter (class in pimlico.datatypes) (class in pimlico.datatypes.parse) copy_dir_with_progress() (in module pimlico.utils.filesystem) CorefCorpus (class in pimlico.datatypes.coref.corenlp) (class in pimlico.datatypes.coref.opennlp) CorefCorpusWriter (class in pimlico.datatypes.coref.corenlp) (class in pimlico.datatypes.coref.opennlp) CoreNLPCorefCorpus (in module pimlico.datatypes) (in module pimlico.datatypes.coref) CoreNLPCorefCorpusWriter (in module pimlico.datatypes) (in module pimlico.datatypes.coref) CorpusAlignmentError, [1] create_from_options() (pimlico.datatypes.base.PimlicoDatatype class method) (pimlico.datatypes.PimlicoDatatype class method) create_pool() (pimlico.core.modules.map.DocumentMapModuleExecutor method) (pimlico.core.modules.map.multiproc.MultiprocessingMapModuleExecutor method) (pimlico.core.modules.map.singleproc.MultiprocessingMapModuleExecutor method) (pimlico.core.modules.map.threaded.ThreadingMapModuleExecutor method) create_queue() (pimlico.core.modules.map.DocumentProcessorPool static method) (pimlico.core.modules.map.multiproc.MultiprocessingMapPool static method) (pimlico.core.modules.map.singleproc.SingleThreadMapPool static method) (pimlico.core.modules.map.threaded.ThreadingMapPool static method)

D

data (pimlico.datatypes.results.NumericResult attribute) data_path (pimlico.datatypes.plotting.PlotOutput attribute) data_ready() (pimlico.core.modules.map.filter.DocumentMapOutputTypeWrapper method) (pimlico.datatypes.Dictionary method) (pimlico.datatypes.NumpyArray method) (pimlico.datatypes.PimlicoDatatype method) (pimlico.datatypes.ScipySparseMatrix method) (pimlico.datatypes.TarredCorpus method) (pimlico.datatypes.WordAnnotationCorpus method) (pimlico.datatypes.XmlDocumentIterator method) (pimlico.datatypes.arrays.NumpyArray method) (pimlico.datatypes.arrays.ScipySparseMatrix method) (pimlico.datatypes.base.PimlicoDatatype method) (pimlico.datatypes.dictionary.Dictionary method) (pimlico.datatypes.tar.TarredCorpus method) (pimlico.datatypes.word2vec.Word2VecModel method) (pimlico.datatypes.word_annotations.WordAnnotationCorpus method) (pimlico.datatypes.xml.XmlDocumentIterator method) DataShell (class in pimlico.cli.shell.base) DATATYPE (pimlico.cli.browser.formatter.DefaultFormatter attribute) (pimlico.cli.browser.formatter.DocumentBrowserFormatter attribute) (pimlico.cli.browser.formatter.InvalidDocumentFormatter attribute) datatype_doc_info (pimlico.datatypes.base.DynamicInputDatatypeRequirement attribute) (pimlico.datatypes.DynamicInputDatatypeRequirement attribute) datatype_full_class_name() (pimlico.datatypes.base.PimlicoDatatype class method) (pimlico.datatypes.PimlicoDatatype class method) datatype_name (pimlico.datatypes.base.DynamicOutputDatatype attribute) (pimlico.datatypes.CandcOutputCorpus attribute) (pimlico.datatypes.CoNLLDependencyParseCorpus attribute) (pimlico.datatypes.CoNLLDependencyParseInputCorpus attribute) (pimlico.datatypes.ConstituencyParseTreeCorpus attribute) (pimlico.datatypes.DynamicOutputDatatype attribute) (pimlico.datatypes.IterableCorpus attribute) (pimlico.datatypes.JsonDocumentCorpus attribute) (pimlico.datatypes.KeyValueListCorpus attribute) (pimlico.datatypes.PimlicoDatatype attribute) (pimlico.datatypes.StanfordDependencyParseCorpus attribute) (pimlico.datatypes.TarredCorpus attribute) (pimlico.datatypes.TermFeatureListCorpus attribute) (pimlico.datatypes.TokenizedCorpus attribute) (pimlico.datatypes.WordAnnotationCorpus attribute) (pimlico.datatypes.base.IterableCorpus attribute) (pimlico.datatypes.base.PimlicoDatatype attribute) (pimlico.datatypes.coref.corenlp.CorefCorpus attribute) (pimlico.datatypes.coref.opennlp.CorefCorpus attribute) (pimlico.datatypes.features.KeyValueListCorpus attribute) (pimlico.datatypes.features.TermFeatureListCorpus attribute) (pimlico.datatypes.jsondoc.JsonDocumentCorpus attribute) (pimlico.datatypes.parse.CandcOutputCorpus attribute) (pimlico.datatypes.parse.CoNLLDependencyParseCorpus attribute) (pimlico.datatypes.parse.CoNLLDependencyParseInputCorpus attribute) (pimlico.datatypes.parse.ConstituencyParseTreeCorpus attribute) (pimlico.datatypes.parse.StanfordDependencyParseCorpus attribute) (pimlico.datatypes.parse.candc.CandcOutputCorpus attribute) (pimlico.datatypes.parse.dependency.CoNLLDependencyParseCorpus attribute) (pimlico.datatypes.parse.dependency.CoNLLDependencyParseInputCorpus attribute) (pimlico.datatypes.parse.dependency.StanfordDependencyParseCorpus attribute) (pimlico.datatypes.tar.TarredCorpus attribute) (pimlico.datatypes.tokenized.TokenizedCorpus attribute) (pimlico.datatypes.word_annotations.WordAnnotationCorpus attribute) DatatypeLoadError, [1] DatatypeWriteError, [1] default() (pimlico.cli.shell.base.DataShell method) DefaultFormatter (class in pimlico.cli.browser.formatter) dependencies (pimlico.core.modules.base.BaseModuleInfo attribute) dependencies() (pimlico.core.dependencies.base.SoftwareDependency method) (pimlico.core.dependencies.java.Py4JSoftwareDependency method) DependencyCheckerError DependencyError

Dictionary (class in pimlico.datatypes) (class in pimlico.datatypes.dictionary) DictionaryWriter (class in pimlico.datatypes) (class in pimlico.datatypes.dictionary) dirsize() (in module pimlico.utils.filesystem) do_EOF() (pimlico.cli.shell.base.DataShell method) doc_iter() (pimlico.datatypes.tar.TarredCorpus method) (pimlico.datatypes.TarredCorpus method) document_preprocessors (pimlico.datatypes.tar.TarredCorpus attribute) (pimlico.datatypes.TarredCorpus attribute) document_to_raw_data() (pimlico.datatypes.CandcOutputCorpusWriter method) (pimlico.datatypes.CoNLLDependencyParseCorpusWriter method) (pimlico.datatypes.CoNLLDependencyParseInputCorpusWriter method) (pimlico.datatypes.ConstituencyParseTreeCorpusWriter method) (pimlico.datatypes.JsonDocumentCorpusWriter method) (pimlico.datatypes.KeyValueListCorpusWriter method) (pimlico.datatypes.SimpleWordAnnotationCorpusWriter method) (pimlico.datatypes.StanfordDependencyParseCorpusWriter method) (pimlico.datatypes.TarredCorpusWriter method) (pimlico.datatypes.TermFeatureListCorpusWriter method) (pimlico.datatypes.TokenizedCorpusWriter method) (pimlico.datatypes.coref.corenlp.CorefCorpusWriter method) (pimlico.datatypes.coref.opennlp.CorefCorpusWriter method) (pimlico.datatypes.features.KeyValueListCorpusWriter method) (pimlico.datatypes.features.TermFeatureListCorpusWriter method) (pimlico.datatypes.jsondoc.JsonDocumentCorpusWriter method) (pimlico.datatypes.parse.CandcOutputCorpusWriter method) (pimlico.datatypes.parse.CoNLLDependencyParseCorpusWriter method) (pimlico.datatypes.parse.CoNLLDependencyParseInputCorpusWriter method) (pimlico.datatypes.parse.ConstituencyParseTreeCorpusWriter method) (pimlico.datatypes.parse.StanfordDependencyParseCorpusWriter method) (pimlico.datatypes.parse.candc.CandcOutputCorpusWriter method) (pimlico.datatypes.parse.dependency.CoNLLDependencyParseCorpusWriter method) (pimlico.datatypes.parse.dependency.CoNLLDependencyParseInputCorpusWriter method) (pimlico.datatypes.parse.dependency.StanfordDependencyParseCorpusWriter method) (pimlico.datatypes.table.IntegerTableDocumentCorpusWriter method) (pimlico.datatypes.tar.TarredCorpusWriter method) (pimlico.datatypes.tokenized.TokenizedCorpusWriter method) (pimlico.datatypes.word_annotations.SimpleWordAnnotationCorpusWriter method) DocumentBrowserFormatter (class in pimlico.cli.browser.formatter) DocumentMapModuleExecutor (class in pimlico.core.modules.map) DocumentMapModuleInfo (class in pimlico.core.modules.map) DocumentMapOutputTypeWrapper (class in pimlico.core.modules.map.filter) DocumentMapProcessMixin (class in pimlico.core.modules.map) DocumentProcessorPool (class in pimlico.core.modules.map) download_file() (in module pimlico.utils.web) DynamicInputDatatypeRequirement (class in pimlico.datatypes) (class in pimlico.datatypes.base) DynamicOutputDatatype (class in pimlico.datatypes) (class in pimlico.datatypes.base)

E

emptyline() (pimlico.cli.shell.base.DataShell method) encode() (pimlico.utils.communicate.StreamCommunicationPacket method) Entity (class in pimlico.datatypes.coref.corenlp) (class in pimlico.datatypes.coref.opennlp) execute() (pimlico.cli.shell.base.ShellCommand method) (pimlico.core.modules.base.BaseModuleExecutor method) (pimlico.core.modules.map.DocumentMapModuleExecutor method) execute_module() (in module pimlico.core.modules.execute) execution_history (pimlico.core.modules.base.BaseModuleInfo attribute)

execution_history_path (pimlico.core.modules.base.BaseModuleInfo attribute) extract_archive() (in module pimlico.utils.filesystem) extract_file() (pimlico.datatypes.tar.TarredCorpus method) (pimlico.datatypes.TarredCorpus method) extract_from_archive() (in module pimlico.utils.filesystem) extract_input_options() (pimlico.core.modules.base.BaseModuleInfo class method)

F

feature_dictionary (pimlico.datatypes.features.IndexedTermFeatureListCorpus attribute) (pimlico.datatypes.IndexedTermFeatureListCorpus attribute) filter() (pimlico.datatypes.dictionary.DictionaryWriter method) (pimlico.datatypes.DictionaryWriter method) filter_document() (pimlico.cli.browser.formatter.DocumentBrowserFormatter method) (pimlico.cli.browser.formatter.InvalidDocumentFormatter method) find_all_data_paths() (pimlico.core.config.PipelineConfig method) find_data_path() (pimlico.core.config.PipelineConfig method) format_document() (pimlico.cli.browser.formatter.DefaultFormatter method) (pimlico.cli.browser.formatter.DocumentBrowserFormatter method) (pimlico.cli.browser.formatter.InvalidDocumentFormatter method)

format_execution_dependency_tree() (in module pimlico.core.modules.execute) format_file_size() (in module pimlico.utils.filesystem) format_option_type() (in module pimlico.core.modules.options) from_java_object() (pimlico.datatypes.coref.opennlp.Entity static method) (pimlico.datatypes.coref.opennlp.Mention static method) from_json() (pimlico.datatypes.coref.corenlp.Mention static method) (pimlico.datatypes.coref.opennlp.Entity static method) (pimlico.datatypes.coref.opennlp.Mention static method)

G

gateway_client_to_running_server() (in module pimlico.core.external.java) generate_contents_page() (in module pimlico.utils.docs.modulegen) generate_docs_for_pimlico_mod() (in module pimlico.utils.docs.modulegen) generate_docs_for_pymod() (in module pimlico.utils.docs.modulegen) get() (pimlico.utils.pipes.OutputQueue method) get_absolute_output_dir() (pimlico.core.modules.base.BaseModuleInfo method) get_all_executed_modules() (pimlico.core.modules.base.BaseModuleInfo method) get_available() (pimlico.utils.pipes.OutputQueue method) get_base_datatype_class() (pimlico.datatypes.AddAnnotationField class method) (pimlico.datatypes.DynamicOutputDatatype method) (pimlico.datatypes.base.DynamicOutputDatatype method) (pimlico.datatypes.word_annotations.AddAnnotationField class method) get_classpath() (in module pimlico.core.dependencies.java) get_classpath_components() (pimlico.core.dependencies.java.JavaDependency method) get_console_logger() (in module pimlico.utils.logging) get_data() (pimlico.datatypes.Dictionary method) (pimlico.datatypes.dictionary.Dictionary method) get_datatype() (pimlico.datatypes.AddAnnotationField method) (pimlico.datatypes.DynamicOutputDatatype method) (pimlico.datatypes.base.DynamicOutputDatatype method) (pimlico.datatypes.word_annotations.AddAnnotationField method) get_dependencies() (in module pimlico.core.config) get_detailed_status() (pimlico.core.modules.base.BaseModuleInfo method) (pimlico.core.modules.map.DocumentMapModuleInfo method) (pimlico.core.modules.multistage.MultistageModuleInfo method) (pimlico.datatypes.IterableCorpus method) (pimlico.datatypes.PimlicoDatatype method) (pimlico.datatypes.base.IterableCorpus method) (pimlico.datatypes.base.PimlicoDatatype method) get_execution_dependency_tree() (pimlico.core.modules.base.BaseModuleInfo method) get_extra_outputs_from_options() (pimlico.core.modules.base.BaseModuleInfo static method) get_head_word() (pimlico.datatypes.coref.opennlp.Entity method) get_input() (pimlico.core.modules.base.BaseModuleInfo method) get_input_datatype() (pimlico.core.modules.base.BaseModuleInfo method) get_input_module_connection() (pimlico.core.modules.base.BaseModuleInfo method)

get_input_software_dependencies() (pimlico.core.modules.base.BaseModuleInfo method) (pimlico.core.modules.multistage.MultistageModuleInfo method) get_key_info_table() (pimlico.core.modules.base.BaseModuleInfo class method) (pimlico.core.modules.multistage.MultistageModuleInfo class method) get_log_file() (in module pimlico.core.logs) get_metadata() (pimlico.core.modules.base.BaseModuleInfo method) get_module_classpath() (in module pimlico.core.dependencies.java) get_module_output_dir() (pimlico.core.modules.base.BaseModuleInfo method) get_module_schedule() (pimlico.core.config.PipelineConfig method) get_next_output_document() (pimlico.core.modules.map.InputQueueFeeder method) get_next_stage() (pimlico.core.modules.multistage.MultistageModuleInfo method) get_nowait() (pimlico.utils.pipes.OutputQueue method) get_output() (pimlico.core.modules.base.BaseModuleInfo method) get_output_datatype() (pimlico.core.modules.base.BaseModuleInfo method) get_output_dir() (pimlico.core.modules.base.BaseModuleInfo method) get_progress_bar() (in module pimlico.utils.progress) get_redirect_func() (in module pimlico.core.external.java) get_software_dependencies() (pimlico.core.modules.base.BaseModuleInfo method) (pimlico.core.modules.multistage.MultistageModuleInfo method) (pimlico.datatypes.PimlicoDatatype method) (pimlico.datatypes.XmlDocumentIterator method) (pimlico.datatypes.base.PimlicoDatatype method) (pimlico.datatypes.word2vec.Word2VecModel method) (pimlico.datatypes.xml.XmlDocumentIterator method) get_struct() (in module pimlico.datatypes.table) get_unused_local_port() (in module pimlico.utils.network) get_unused_local_ports() (in module pimlico.utils.network) get_writer() (pimlico.core.modules.map.DocumentMapModuleInfo method) get_writers() (pimlico.core.modules.map.DocumentMapModuleInfo method)

H

help_text (pimlico.cli.shell.base.ShellCommand attribute)

I

import_package() (pimlico.core.dependencies.python.PythonPackageDependency method) IndexedTermFeatureListCorpus (class in pimlico.datatypes) (class in pimlico.datatypes.features) IndexedTermFeatureListCorpusWriter (class in pimlico.datatypes) (class in pimlico.datatypes.features) infinite_cycle() (in module pimlico.utils.core) input_datatype_list() (in module pimlico.utils.docs.modulegen) input_datatype_text() (in module pimlico.utils.docs.modulegen) input_module_factory() (in module pimlico.core.modules.inputs) input_module_options (pimlico.datatypes.base.PimlicoDatatype attribute) (pimlico.datatypes.PimlicoDatatype attribute) (pimlico.datatypes.XmlDocumentIterator attribute) (pimlico.datatypes.xml.XmlDocumentIterator attribute) input_names (pimlico.core.modules.base.BaseModuleInfo attribute) input_ready() (pimlico.core.modules.base.BaseModuleInfo method) InputModuleInfo (class in pimlico.core.modules.inputs) InputQueueFeeder (class in pimlico.core.modules.map) insert_module() (pimlico.core.config.PipelineConfig method) install() (in module pimlico.core.dependencies.base) (pimlico.core.dependencies.base.SoftwareDependency method) (pimlico.core.dependencies.java.JavaJarsDependency method) (pimlico.core.dependencies.java.Py4JSoftwareDependency method) (pimlico.core.dependencies.python.PythonPackageOnPip method) install_cmd() (in module pimlico.cli.check) install_core_dependencies() (in module pimlico) installable() (pimlico.core.dependencies.base.LegacyDatatypeDependencies method) (pimlico.core.dependencies.base.LegacyModuleDependencies method) (pimlico.core.dependencies.base.SoftwareDependency method) (pimlico.core.dependencies.base.SystemCommandDependency method) (pimlico.core.dependencies.java.JavaDependency method) (pimlico.core.dependencies.java.Py4JSoftwareDependency method) (pimlico.core.dependencies.python.PythonPackageOnPip method) (pimlico.core.dependencies.python.PythonPackageSystemwideInstall method)

installation_instructions() (pimlico.core.dependencies.base.LegacyDatatypeDependencies method) (pimlico.core.dependencies.base.LegacyModuleDependencies method) (pimlico.core.dependencies.base.SoftwareDependency method) (pimlico.core.dependencies.python.PythonPackageSystemwideInstall method) InstallationError instantiate_output_datatype() (pimlico.core.modules.base.BaseModuleInfo method) (pimlico.core.modules.inputs.InputModuleInfo method) IntegerTableDocumentCorpus (class in pimlico.datatypes.table) IntegerTableDocumentCorpusWriter (class in pimlico.datatypes.table) InternalModuleConnection (class in pimlico.core.modules.multistage) invalid_doc_on_error() (in module pimlico.core.modules.map) invalid_docs_on_error() (in module pimlico.core.modules.map) invalid_document_or_text() (pimlico.datatypes.base.InvalidDocument static method) (pimlico.datatypes.InvalidDocument static method) InvalidDocument (class in pimlico.datatypes) (class in pimlico.datatypes.base) InvalidDocumentFormatter (class in pimlico.cli.browser.formatter) is_filter() (pimlico.core.modules.base.BaseModuleInfo class method) is_identifier() (in module pimlico.utils.core) is_input() (pimlico.core.modules.base.BaseModuleInfo class method) is_multiple_input() (pimlico.core.modules.base.BaseModuleInfo method) IterableCorpus (class in pimlico.datatypes) (class in pimlico.datatypes.base) IterableCorpusWriter (class in pimlico.datatypes) (class in pimlico.datatypes.base)

J

jars (pimlico.core.dependencies.java.Py4JSoftwareDependency attribute) JavaDependency (class in pimlico.core.dependencies.java) JavaJarsDependency (class in pimlico.core.dependencies.java)

JavaProcessError JsonDocumentCorpus (class in pimlico.datatypes) (class in pimlico.datatypes.jsondoc) JsonDocumentCorpusWriter (class in pimlico.datatypes) (class in pimlico.datatypes.jsondoc)

K

KeyValueListCorpus (class in pimlico.datatypes) (class in pimlico.datatypes.features)

KeyValueListCorpusWriter (class in pimlico.datatypes) (class in pimlico.datatypes.features)

L

label (pimlico.datatypes.results.NumericResult attribute) launch_gateway() (in module pimlico.core.external.java) launch_shell() (in module pimlico.cli.shell.runner) LegacyDatatypeDependencies (class in pimlico.core.dependencies.base) LegacyModuleDependencies (class in pimlico.core.dependencies.base) length (pimlico.utils.communicate.StreamCommunicationPacket attribute) limited_shuffle() (in module pimlico.utils.probability)

list_archive_iter() (pimlico.datatypes.tar.TarredCorpus method) (pimlico.datatypes.TarredCorpus method) load() (pimlico.core.config.PipelineConfig static method) (pimlico.datatypes.InvalidDocument static method) (pimlico.datatypes.base.InvalidDocument static method) load_datatype() (in module pimlico.datatypes) (in module pimlico.datatypes.base) load_formatter() (in module pimlico.cli.browser.formatter) load_model() (pimlico.datatypes.word2vec.Word2VecModel method) load_module_executor() (in module pimlico.core.modules.base) load_module_info() (in module pimlico.core.modules.base) (pimlico.core.config.PipelineConfig method)

M

main_module (pimlico.core.modules.base.BaseModuleInfo attribute) make_py4j_errors_safe() (in module pimlico.core.external.java) make_table() (in module pimlico.utils.docs.rest) Mention (class in pimlico.datatypes.coref.corenlp) (class in pimlico.datatypes.coref.opennlp) metadata (pimlico.datatypes.base.PimlicoDatatype attribute) (pimlico.datatypes.PimlicoDatatype attribute) metadata_filename (pimlico.core.modules.base.BaseModuleInfo attribute) missing_data() (pimlico.core.modules.base.BaseModuleInfo method) model (pimlico.datatypes.word2vec.Word2VecModel attribute) module_executable (pimlico.core.modules.base.BaseModuleInfo attribute) (pimlico.core.modules.inputs.InputModuleInfo attribute) (pimlico.core.modules.multistage.MultistageModuleInfo attribute) module_executor_override (pimlico.core.modules.base.BaseModuleInfo attribute) module_inputs (pimlico.core.modules.base.BaseModuleInfo attribute) module_optional_outputs (pimlico.core.modules.base.BaseModuleInfo attribute) module_options (pimlico.core.modules.base.BaseModuleInfo attribute) module_outputs (pimlico.core.modules.base.BaseModuleInfo attribute) (pimlico.core.modules.map.DocumentMapModuleInfo attribute) module_package_name() (pimlico.core.modules.base.BaseModuleInfo class method) module_readable_name (pimlico.core.modules.base.BaseModuleInfo attribute) module_status() (in module pimlico.cli.status) module_status_color() (in module pimlico.cli.status) module_type_name (pimlico.core.modules.base.BaseModuleInfo attribute) (pimlico.core.modules.inputs.InputModuleInfo attribute) ModuleAlreadyCompletedError ModuleConnection (class in pimlico.core.modules.multistage)

ModuleExecutionError ModuleExecutorLoadError ModuleInfoLoadError ModuleInputConnection (class in pimlico.core.modules.multistage) ModuleNotReadyError ModuleOptionParseError ModuleOutputConnection (class in pimlico.core.modules.multistage) modules (pimlico.core.config.PipelineConfig attribute) ModuleStage (class in pimlico.core.modules.multistage) ModuleTypeError multiline_tablate() (in module pimlico.utils.format) multiply_alternatives() (in module pimlico.core.config) multiprocessing_executor_factory() (in module pimlico.core.modules.map.multiproc) MultiprocessingMapModuleExecutor (class in pimlico.core.modules.map.multiproc) (class in pimlico.core.modules.map.singleproc) MultiprocessingMapPool (class in pimlico.core.modules.map.multiproc) MultiprocessingMapProcess (class in pimlico.core.modules.map.multiproc) multistage_module() (in module pimlico.core.modules.multistage) MultistageModuleInfo (class in pimlico.core.modules.multistage) MultistageModulePreparationError multiwith() (in module pimlico.utils.core)

N

new_client() (pimlico.core.external.java.Py4JInterface method) new_filename() (in module pimlico.utils.filesystem) no_retry_gateway() (in module pimlico.core.external.java) non_filter_datatype (pimlico.core.modules.map.filter.DocumentMapOutputTypeWrapper attribute) NonPTBTagError normalize_cell() (in module pimlico.utils.docs.rest)

notify_no_more_inputs() (pimlico.core.modules.map.DocumentMapProcessMixin method) (pimlico.core.modules.map.DocumentProcessorPool method) (pimlico.core.modules.map.multiproc.MultiprocessingMapPool method) (pimlico.core.modules.map.multiproc.MultiprocessingMapProcess method) (pimlico.core.modules.map.singleproc.SingleThreadMapWorker method) (pimlico.core.modules.map.threaded.ThreadingMapThread method) NumericResult (class in pimlico.datatypes.results) NumericResultWriter (class in pimlico.datatypes.results) NumpyArray (class in pimlico.datatypes) (class in pimlico.datatypes.arrays) NumpyArrayWriter (class in pimlico.datatypes) (class in pimlico.datatypes.arrays)

O

OpenNLPCorefCorpus (in module pimlico.datatypes) (in module pimlico.datatypes.coref) OpenNLPCorefCorpusWriter (in module pimlico.datatypes) (in module pimlico.datatypes.coref) opt_type_help() (in module pimlico.core.modules.options) output_datatype_text() (in module pimlico.utils.docs.modulegen) output_name (pimlico.core.modules.map.filter.DocumentMapOutputTypeWrapper attribute)

output_names (pimlico.core.modules.base.BaseModuleInfo attribute) output_p4j_error_info() (in module pimlico.core.external.java) OutputConsumer (class in pimlico.core.external.java) OutputQueue (class in pimlico.utils.pipes)

P

path_relative_to_config() (pimlico.core.config.PipelineConfig method) pdf_path (pimlico.datatypes.plotting.PlotOutput attribute) pimlico (module) pimlico.cli (module) pimlico.cli.browser (module) pimlico.cli.browser.formatter (module) pimlico.cli.check (module) pimlico.cli.shell (module) pimlico.cli.shell.base (module) pimlico.cli.shell.commands (module) pimlico.cli.shell.runner (module) pimlico.cli.status (module) pimlico.core (module) pimlico.core.config (module) pimlico.core.dependencies (module) pimlico.core.dependencies.base (module) pimlico.core.dependencies.core (module) pimlico.core.dependencies.java (module) pimlico.core.dependencies.python (module) pimlico.core.external (module) pimlico.core.external.java (module) pimlico.core.logs (module) pimlico.core.modules (module) pimlico.core.modules.base (module) pimlico.core.modules.execute (module) pimlico.core.modules.inputs (module) pimlico.core.modules.map (module) pimlico.core.modules.map.filter (module) pimlico.core.modules.map.multiproc (module) pimlico.core.modules.map.singleproc (module) pimlico.core.modules.map.threaded (module) pimlico.core.modules.multistage (module) pimlico.core.modules.options (module) pimlico.core.paths (module) pimlico.datatypes (module) pimlico.datatypes.arrays (module) pimlico.datatypes.base (module) pimlico.datatypes.caevo (module) pimlico.datatypes.coref (module) pimlico.datatypes.coref.corenlp (module) pimlico.datatypes.coref.opennlp (module) pimlico.datatypes.dictionary (module) pimlico.datatypes.features (module) pimlico.datatypes.jsondoc (module) pimlico.datatypes.parse (module) pimlico.datatypes.parse.candc (module) pimlico.datatypes.parse.dependency (module) pimlico.datatypes.plotting (module) pimlico.datatypes.results (module) pimlico.datatypes.table (module) pimlico.datatypes.tar (module) pimlico.datatypes.tokenized (module) pimlico.datatypes.word2vec (module) pimlico.datatypes.word_annotations (module) pimlico.datatypes.xml (module) pimlico.modules (module) pimlico.modules.caevo (module) pimlico.modules.candc (module) pimlico.modules.corenlp (module) pimlico.modules.corpora (module) pimlico.modules.corpora.format (module) pimlico.modules.corpora.split (module) pimlico.modules.corpora.subset (module) pimlico.modules.corpora.tar (module) pimlico.modules.corpora.tar_filter (module) pimlico.modules.corpora.vocab_builder (module) pimlico.modules.embeddings (module) pimlico.modules.embeddings.dependencies (module) pimlico.modules.embeddings.word2vec (module) pimlico.modules.features (module) pimlico.modules.features.term_feature_compiler (module)

pimlico.modules.features.term_feature_matrix_builder (module) pimlico.modules.features.vocab_builder (module) pimlico.modules.features.vocab_mapper (module) pimlico.modules.malt (module) pimlico.modules.malt.conll_parser_input (module) pimlico.modules.malt.parse (module) pimlico.modules.opennlp (module) pimlico.modules.opennlp.coreference (module) pimlico.modules.opennlp.parse (module) pimlico.modules.opennlp.pos (module) pimlico.modules.opennlp.tokenize (module) pimlico.modules.regex (module) pimlico.modules.regex.annotated_text (module) pimlico.modules.sklearn (module) pimlico.modules.sklearn.matrix_factorization (module) pimlico.modules.visualization (module) pimlico.modules.visualization.bar_chart (module) pimlico.utils (module) pimlico.utils.communicate (module) pimlico.utils.core (module) pimlico.utils.docs (module) pimlico.utils.docs.modulegen (module) pimlico.utils.docs.rest (module) pimlico.utils.filesystem (module) pimlico.utils.format (module) pimlico.utils.linguistic (module) pimlico.utils.logging (module) pimlico.utils.network (module) pimlico.utils.pipes (module) pimlico.utils.pos (module) pimlico.utils.probability (module) pimlico.utils.progress (module) pimlico.utils.strings (module) pimlico.utils.timeout (module) pimlico.utils.web (module) PimlicoDatatype (class in pimlico.datatypes) (class in pimlico.datatypes.base) PimlicoDatatypeWriter (class in pimlico.datatypes) (class in pimlico.datatypes.base) PimlicoJavaLibrary (class in pimlico.core.dependencies.java) PipelineCheckError PipelineConfig (class in pimlico.core.config) PipelineConfigParseError PipelineStructureError plot() (pimlico.datatypes.plotting.PlotOutput method) PlotOutput (class in pimlico.datatypes.plotting) PlotOutputWriter (class in pimlico.datatypes.plotting) POOL_TYPE (pimlico.core.modules.map.multiproc.MultiprocessingMapModuleExecutor attribute) (pimlico.core.modules.map.singleproc.MultiprocessingMapModuleExecutor attribute) (pimlico.core.modules.map.threaded.ThreadingMapModuleExecutor attribute) pos_tag_to_ptb() (in module pimlico.utils.pos) pos_tags_to_ptb() (in module pimlico.utils.pos) postloop() (pimlico.cli.shell.base.DataShell method) postprocess() (pimlico.core.modules.map.DocumentMapModuleExecutor method) (pimlico.core.modules.map.multiproc.MultiprocessingMapModuleExecutor method) (pimlico.core.modules.map.singleproc.MultiprocessingMapModuleExecutor method) (pimlico.core.modules.map.threaded.ThreadingMapModuleExecutor method) preloop() (pimlico.cli.shell.base.DataShell method) prepare_data() (pimlico.datatypes.base.PimlicoDatatype method) (pimlico.datatypes.PimlicoDatatype method) (pimlico.datatypes.XmlDocumentIterator method) (pimlico.datatypes.xml.XmlDocumentIterator method) preprocess() (pimlico.core.modules.map.DocumentMapModuleExecutor method) preprocess_config_file() (in module pimlico.core.config) print_dependency_leaf_problems() (in module pimlico.core.config) print_missing_dependencies() (in module pimlico.core.config) problems() (pimlico.core.dependencies.base.LegacyDatatypeDependencies method) (pimlico.core.dependencies.base.LegacyModuleDependencies method) (pimlico.core.dependencies.base.SoftwareDependency method) (pimlico.core.dependencies.base.SystemCommandDependency method) (pimlico.core.dependencies.java.JavaDependency method) (pimlico.core.dependencies.python.PythonPackageDependency method) process_config() (pimlico.core.modules.base.BaseModuleInfo class method) process_document() (pimlico.core.modules.map.DocumentMapProcessMixin method) (pimlico.datatypes.CaevoCorpus method) (pimlico.datatypes.CandcOutputCorpus method) (pimlico.datatypes.CoNLLDependencyParseCorpus method) (pimlico.datatypes.CoNLLDependencyParseInputCorpus method) (pimlico.datatypes.ConstituencyParseTreeCorpus method) (pimlico.datatypes.JsonDocumentCorpus method) (pimlico.datatypes.KeyValueListCorpus method) (pimlico.datatypes.StanfordDependencyParseCorpus method) (pimlico.datatypes.TarredCorpus method) (pimlico.datatypes.TermFeatureListCorpus method) (pimlico.datatypes.TokenizedCorpus method) (pimlico.datatypes.WordAnnotationCorpus method) (pimlico.datatypes.caevo.CaevoCorpus method) (pimlico.datatypes.coref.corenlp.CorefCorpus method) (pimlico.datatypes.coref.opennlp.CorefCorpus method) (pimlico.datatypes.features.KeyValueListCorpus method) (pimlico.datatypes.features.TermFeatureListCorpus method) (pimlico.datatypes.jsondoc.JsonDocumentCorpus method) (pimlico.datatypes.parse.CandcOutputCorpus method) (pimlico.datatypes.parse.CoNLLDependencyParseCorpus method) (pimlico.datatypes.parse.CoNLLDependencyParseInputCorpus method) (pimlico.datatypes.parse.ConstituencyParseTreeCorpus method) (pimlico.datatypes.parse.StanfordDependencyParseCorpus method) (pimlico.datatypes.parse.candc.CandcOutputCorpus method) (pimlico.datatypes.parse.dependency.CoNLLDependencyParseCorpus method) (pimlico.datatypes.parse.dependency.CoNLLDependencyParseInputCorpus method) (pimlico.datatypes.parse.dependency.StanfordDependencyParseCorpus method) (pimlico.datatypes.table.IntegerTableDocumentCorpus method) (pimlico.datatypes.tar.TarredCorpus method) (pimlico.datatypes.tokenized.TokenizedCorpus method) (pimlico.datatypes.word_annotations.WordAnnotationCorpus method) process_documents() (pimlico.core.modules.map.DocumentMapProcessMixin method) process_module_options() (in module pimlico.core.modules.options) (pimlico.core.modules.base.BaseModuleInfo class method) PROCESS_TYPE (pimlico.core.modules.map.multiproc.MultiprocessingMapPool attribute) ProcessOutput (class in pimlico.core.modules.map) ProgressBarIter (class in pimlico.utils.progress) prompt (pimlico.cli.shell.base.DataShell attribute) Py4JInterface (class in pimlico.core.external.java) Py4JSafeJavaError Py4JSoftwareDependency (class in pimlico.core.dependencies.java) PythonPackageDependency (class in pimlico.core.dependencies.python) PythonPackageOnPip (class in pimlico.core.dependencies.python) PythonPackageSystemwideInstall (class in pimlico.core.dependencies.python)

Q

qget() (in module pimlico.utils.pipes)

R

RAW_INPUT (pimlico.cli.browser.formatter.DocumentBrowserFormatter attribute) read() (pimlico.utils.communicate.StreamCommunicationPacket static method) read_annotation_fields() (pimlico.datatypes.word_annotations.WordAnnotationCorpus method) (pimlico.datatypes.WordAnnotationCorpus method) read_rows() (pimlico.datatypes.table.IntegerTableDocumentCorpus method) recursive_deps() (in module pimlico.core.dependencies.base) remove_duplicates() (in module pimlico.utils.core) remove_temporary_redirects() (pimlico.core.external.java.OutputConsumer method)

requires_data_preparation (pimlico.datatypes.base.PimlicoDatatype attribute) (pimlico.datatypes.PimlicoDatatype attribute) (pimlico.datatypes.XmlDocumentIterator attribute) (pimlico.datatypes.xml.XmlDocumentIterator attribute) reset_execution() (pimlico.core.modules.base.BaseModuleInfo method) (pimlico.core.modules.multistage.MultistageModuleInfo method) result (pimlico.datatypes.results.NumericResult attribute) retrieve_processing_status() (pimlico.core.modules.map.DocumentMapModuleExecutor method) retry_open() (in module pimlico.utils.filesystem) row_size (pimlico.datatypes.table.IntegerTableDocumentCorpus attribute) run() (pimlico.core.external.java.OutputConsumer method) (pimlico.core.modules.map.InputQueueFeeder method) (pimlico.core.modules.map.multiproc.MultiprocessingMapProcess method) (pimlico.core.modules.map.singleproc.SingleThreadMapWorker method) (pimlico.core.modules.map.threaded.ThreadingMapThread method)

S

SafeProgressBar (class in pimlico.utils.progress) ScipySparseMatrix (class in pimlico.datatypes) (class in pimlico.datatypes.arrays) ScipySparseMatrixWriter (class in pimlico.datatypes) (class in pimlico.datatypes.arrays) script_path (pimlico.datatypes.plotting.PlotOutput attribute) sentence_boundary_re (pimlico.datatypes.word_annotations.WordAnnotationCorpus attribute) (pimlico.datatypes.WordAnnotationCorpus attribute) set_array() (pimlico.datatypes.arrays.NumpyArrayWriter method) (pimlico.datatypes.NumpyArrayWriter method) set_matrix() (pimlico.datatypes.arrays.ScipySparseMatrixWriter method) (pimlico.datatypes.ScipySparseMatrixWriter method) set_metadata_value() (pimlico.core.modules.base.BaseModuleInfo method) set_metadata_values() (pimlico.core.modules.base.BaseModuleInfo method) set_up() (pimlico.core.modules.map.DocumentMapProcessMixin method) shell_cmd() (in module pimlico.cli.shell.runner) shell_commands (pimlico.datatypes.base.PimlicoDatatype attribute) (pimlico.datatypes.PimlicoDatatype attribute) (pimlico.datatypes.word2vec.Word2VecModel attribute) ShellCommand (class in pimlico.cli.shell.base) ShellError shutdown() (pimlico.core.modules.map.multiproc.MultiprocessingMapPool method) (pimlico.core.modules.map.singleproc.SingleThreadMapPool method) (pimlico.core.modules.map.threaded.ThreadingMapPool method) SimpleWordAnnotationCorpusWriter (class in pimlico.datatypes) (class in pimlico.datatypes.word_annotations) single_process_executor_factory() (in module pimlico.core.modules.map.singleproc) SingleThreadMapPool (class in pimlico.core.modules.map.singleproc) SingleThreadMapWorker (class in pimlico.core.modules.map.singleproc) skip_invalid() (in module pimlico.core.modules.map)

skip_invalids() (in module pimlico.core.modules.map) slice_progress() (in module pimlico.utils.progress) SoftwareDependency (class in pimlico.core.dependencies.base) stages (pimlico.core.modules.multistage.MultistageModuleInfo attribute) StanfordDependencyParseCorpus (class in pimlico.datatypes) (class in pimlico.datatypes.parse) (class in pimlico.datatypes.parse.dependency) StanfordDependencyParseCorpusWriter (class in pimlico.datatypes) (class in pimlico.datatypes.parse) (class in pimlico.datatypes.parse.dependency) start() (pimlico.core.external.java.Py4JInterface method) start_java_process() (in module pimlico.core.external.java) start_worker() (pimlico.core.modules.map.multiproc.MultiprocessingMapPool method) (pimlico.core.modules.map.singleproc.SingleThreadMapPool method) (pimlico.core.modules.map.threaded.ThreadingMapPool method) status (pimlico.core.modules.base.BaseModuleInfo attribute) (pimlico.core.modules.multistage.MultistageModuleInfo attribute) status_cmd() (in module pimlico.cli.status) status_colored() (in module pimlico.cli.status) stop() (pimlico.core.external.java.Py4JInterface method) StopProcessing str_to_bool() (in module pimlico.core.modules.options) StreamCommunicationError StreamCommunicationPacket (class in pimlico.utils.communicate) strip_punctuation() (in module pimlico.utils.linguistic) SystemCommandDependency (class in pimlico.core.dependencies.base)

T

table_div() (in module pimlico.utils.docs.rest) TarredCorpus (class in pimlico.datatypes) (class in pimlico.datatypes.tar) TarredCorpusIterationError, [1] TarredCorpusWriter (class in pimlico.datatypes) (class in pimlico.datatypes.tar) tear_down() (pimlico.core.modules.map.DocumentMapProcessMixin method) term_dictionary (pimlico.datatypes.features.IndexedTermFeatureListCorpus attribute) (pimlico.datatypes.IndexedTermFeatureListCorpus attribute) TermFeatureListCorpus (class in pimlico.datatypes) (class in pimlico.datatypes.features) TermFeatureListCorpusWriter (class in pimlico.datatypes) (class in pimlico.datatypes.features) THREAD_TYPE (pimlico.core.modules.map.singleproc.SingleThreadMapPool attribute) (pimlico.core.modules.map.threaded.ThreadingMapPool attribute) threading_executor_factory() (in module pimlico.core.modules.map.threaded) ThreadingMapModuleExecutor (class in pimlico.core.modules.map.threaded) ThreadingMapPool (class in pimlico.core.modules.map.threaded)

ThreadingMapThread (class in pimlico.core.modules.map.threaded) timeout() (in module pimlico.utils.timeout) timeout_process() (in module pimlico.utils.communicate) title_box() (in module pimlico.utils.format) to_json_dict() (pimlico.datatypes.coref.corenlp.Mention method) (pimlico.datatypes.coref.opennlp.Entity method) (pimlico.datatypes.coref.opennlp.Mention method) TokenizedCorpus (class in pimlico.datatypes) (class in pimlico.datatypes.tokenized) TokenizedCorpusWriter (class in pimlico.datatypes) (class in pimlico.datatypes.tokenized) trim_docstring() (in module pimlico.utils.docs) truncate() (in module pimlico.utils.strings) typecheck_inputs() (pimlico.core.modules.base.BaseModuleInfo method) (pimlico.core.modules.multistage.MultistageModuleInfo method) TypeCheckError

U

unpacker (pimlico.datatypes.table.IntegerTableDocumentCorpus attribute) update() (pimlico.utils.progress.SafeProgressBar method)

update_processing_status() (pimlico.core.modules.map.DocumentMapModuleExecutor method)

V

var_substitute() (in module pimlico.core.config)

W

Word2VecModel (class in pimlico.datatypes.word2vec) Word2VecModelWriter (class in pimlico.datatypes.word2vec) word_boundary (pimlico.datatypes.word_annotations.WordAnnotationCorpus attribute) (pimlico.datatypes.WordAnnotationCorpus attribute) word_re (pimlico.datatypes.word_annotations.WordAnnotationCorpus attribute) (pimlico.datatypes.WordAnnotationCorpus attribute) WordAnnotationCorpus (class in pimlico.datatypes) (class in pimlico.datatypes.word_annotations) WordAnnotationCorpusWithRequiredFields (class in pimlico.datatypes) (class in pimlico.datatypes.word_annotations) WordAnnotationCorpusWriter (class in pimlico.datatypes) (class in pimlico.datatypes.word_annotations)

WorkerShutdownError WorkerStartupError wrap_module_info_as_filter() (in module pimlico.core.modules.map.filter) wrapped_module_info (pimlico.core.modules.map.filter.DocumentMapOutputTypeWrapper attribute) write_dictionaries() (pimlico.datatypes.features.IndexedTermFeatureListCorpusWriter method) (pimlico.datatypes.IndexedTermFeatureListCorpusWriter method) write_metadata() (pimlico.datatypes.base.PimlicoDatatypeWriter method) (pimlico.datatypes.PimlicoDatatypeWriter method)

X

XmlDocumentIterator (class in pimlico.datatypes) (class in pimlico.datatypes.xml)